mlsanityData to 14 Oct 2026

Shortcut Learning of Large Language Models in Natural Language Understanding

arXiv 2208.11857 ↗First posted 25 Aug 2022cs.CL cs.LGcited by 85

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly affected their generalizability and adversarial robustness. In this paper, we provide a review of recent developments that address the shortcut learning and robustness challenge of LLMs. We first introduce the concepts of shortcut learning of language models. We then introduce methods to identify shortcut learning behavior in language models, characterize the reasons for shortcut learning, as well as introduce mitigation solutions. Finally, we discuss key research challenges and potential research directions in order to advance the field of LLMs.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Builds on 80 of its 101 references that are in the map. First posted on arXiv 25 Aug 2022.

Builds on

80 of 101 references.

References · 80

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  9. 2019Invariant Risk Minimizationcited by 1,854
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  12. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
38 more
  1. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  2. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  3. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  4. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 876
  5. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  6. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  7. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  8. 2018Annotation Artifacts in Natural Language Inference Datacited by 671
  9. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  10. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  11. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  12. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  13. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 351
  14. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  15. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 339
  16. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  17. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 326
  18. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
  19. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  20. 2021Gradient Matching for Domain Generalizationcited by 258
  21. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 232
  22. 2019Probing Neural Network Comprehension of Natural Language Argumentscited by 214
  23. 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 177
  24. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  25. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 158
  26. 2021A Universal Law of Robustness via Isoperimetrycited by 151
  27. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  28. 2019Towards Debiasing Fact Verification Modelscited by 143
  29. 2020An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Modelscited by 134
  30. 2020What shapes feature representations? Exploring datasets, architectures, and trainingcited by 126
  31. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  32. 2019Unlearn Dataset Bias in Natural Language Inference by Fitting the Residualcited by 119
  33. 2020Towards Debiasing NLU Models from Unknown Biasescited by 116
  34. 2021Can contrastive learning avoid shortcut solutions?cited by 114
  35. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 108
  36. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 97
  37. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 91
  38. 2020Syntactic Data Augmentation Increases Robustness to Inference Heuristicscited by 86

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 16; 2024: 33; 2025: 19; 2026: 12.

85 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  3. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 512
  4. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 411
  5. 2023Explainability for Large Language Models: A Surveycited by 333
  6. 2023Large Language Models in Law: A Surveycited by 128
  7. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  8. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 111
  9. 2024ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identificationcited by 93
  10. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  11. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 88
  12. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
38 more
  1. 2023Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learningcited by 69
  2. 2024Can Language Models Learn to Skip Steps?cited by 59
  3. 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 49
  4. 2023Testing AI on language comprehension tasks reveals insensitivity to underlying meaningcited by 45
  5. 2024The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learningcited by 41
  6. 2024On the Challenges and Opportunities in Generative AIcited by 31
  7. 2024Source Code Summarization in the Era of Large Language Modelscited by 31
  8. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentationcited by 31
  9. 2022DISCO: Distilling Counterfactuals with Large Language Modelscited by 30
  10. 2023Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learningcited by 30
  11. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  12. 2023Fool Your (Vision and) Language Model With Embarrassingly Simple Permutationscited by 25
  13. 2024ImageNet3D: Towards General-Purpose Object-Level 3D Understandingcited by 25
  14. 2022Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learnerscited by 22
  15. 2025Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safetycited by 22
  16. 2024Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theorycited by 19
  17. 2024Large Language Model Benchmarks in Medical Taskscited by 17
  18. 2024The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Modelscited by 15
  19. 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systemscited by 15
  20. 2023Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantizationcited by 14
  21. 2024Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoringcited by 13
  22. 2023Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?cited by 12
  23. 2024Co-occurrence is not Factual Association in Language Modelscited by 12
  24. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  25. 2022Feature-Level Debiased Natural Language Understandingcited by 10
  26. 2024ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Predictioncited by 10
  27. 2025STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reportscited by 10
  28. 2025Do AI Models Perform Human-like Abstract Reasoning Across Modalities?cited by 10
  29. 2024Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictionscited by 9
  30. 2024Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answerscited by 9
  31. 2024ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarizationcited by 8
  32. 2025Mechanistic Indicators of Understanding in Large Language Modelscited by 8
  33. 2024From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistencycited by 7
  34. 2023Does Deep Learning Learn to Abstract? A Systematic Probing Frameworkcited by 6
  35. 2023Controlling Learned Effects to Reduce Spurious Correlations in Text Classifierscited by 5
  36. 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Modelscited by 5
  37. 2022A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehensioncited by 4
  38. 2024Learning Shortcuts: On the Misleading Promise of NLU in Language Modelscited by 4

50 most cited of 85 All 85 (JSON)